JinaChat Authentication

[benman1]

System Info

langchain-0.0.229 python 3.10

Who can help?

@delgermurun

Information

• [X] The official example notebooks/scripts
• [ ] My own modified scripts

Related Components

• [X] LLMs/Chat Models
• [ ] Embedding Models
• [ ] Prompts / Prompt Templates / Prompt Selectors
• [ ] Output Parsers
• [ ] Document Loaders
• [ ] Vector Stores / Retrievers
• [ ] Memory
• [ ] Agents / Agent Executors
• [ ] Tools / Toolkits
• [ ] Chains
• [ ] Callbacks/Tracing
• [ ] Async

Reproduction

import os
from langchain.chat_models import JinaChat
from langchain.schema import HumanMessage

os.environ["JINACHAT_API_KEY"] = "..."  # from https://cloud.jina.ai/settings/tokens
chat = JinaChat(temperature=0)

messages = [
    HumanMessage(
        content="Translate this sentence from English to French: I love you!"
    )
]
print(chat(messages))

Expected behavior

Expected output: Je t'aime Actual output:

---------------------------------------------------------------------------

AuthenticationError                       Traceback (most recent call last)

Cell In[7], line 10
      3 chat = JinaChat(temperature=0)
      5 messages = [
      6     HumanMessage(
      7         content="Translate this sentence from English to French: I love generative AI!"
      8     )
      9 ]
---> 10 chat(messages)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/base.py:349, in BaseChatModel.__call__(self, messages, stop, callbacks, **kwargs)
    342 def __call__(
    343     self,
    344     messages: List[BaseMessage],
   (...)
    347     **kwargs: Any,
    348 ) -> BaseMessage:
--> 349     generation = self.generate(
    350         [messages], stop=stop, callbacks=callbacks, **kwargs
    351     ).generations[0][0]
    352     if isinstance(generation, ChatGeneration):
    353         return generation.message

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/base.py:125, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, **kwargs)
    123         if run_managers:
    124             run_managers[i].on_llm_error(e)
--> 125         raise e
    126 flattened_outputs = [
    127     LLMResult(generations=[res.generations], llm_output=res.llm_output)
    128     for res in results
    129 ]
    130 llm_output = self._combine_llm_outputs([res.llm_output for res in results])

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/base.py:115, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, **kwargs)
    112 for i, m in enumerate(messages):
    113     try:
    114         results.append(
--> 115             self._generate_with_cache(
    116                 m,
    117                 stop=stop,
    118                 run_manager=run_managers[i] if run_managers else None,
    119                 **kwargs,
    120             )
    121         )
    122     except (KeyboardInterrupt, Exception) as e:
    123         if run_managers:

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/base.py:262, in BaseChatModel._generate_with_cache(self, messages, stop, run_manager, **kwargs)
    258     raise ValueError(
    259         "Asked to cache, but no cache found at `langchain.cache`."
    260     )
    261 if new_arg_supported:
--> 262     return self._generate(
    263         messages, stop=stop, run_manager=run_manager, **kwargs
    264     )
    265 else:
    266     return self._generate(messages, stop=stop, **kwargs)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/jinachat.py:288, in JinaChat._generate(self, messages, stop, run_manager, **kwargs)
    281     message = _convert_dict_to_message(
    282         {
    283             "content": inner_completion,
    284             "role": role,
    285         }
    286     )
    287     return ChatResult(generations=[ChatGeneration(message=message)])
--> 288 response = self.completion_with_retry(messages=message_dicts, **params)
    289 return self._create_chat_result(response)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/jinachat.py:244, in JinaChat.completion_with_retry(self, **kwargs)
    240 @retry_decorator
    241 def _completion_with_retry(**kwargs: Any) -> Any:
    242     return self.client.create(**kwargs)
--> 244 return _completion_with_retry(**kwargs)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/tenacity/__init__.py:289, in BaseRetrying.wraps.<locals>.wrapped_f(*args, **kw)
    287 @functools.wraps(f)
    288 def wrapped_f(*args: t.Any, **kw: t.Any) -> t.Any:
--> 289     return self(f, *args, **kw)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/tenacity/__init__.py:379, in Retrying.__call__(self, fn, *args, **kwargs)
    377 retry_state = RetryCallState(retry_object=self, fn=fn, args=args, kwargs=kwargs)
    378 while True:
--> 379     do = self.iter(retry_state=retry_state)
    380     if isinstance(do, DoAttempt):
    381         try:

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/tenacity/__init__.py:314, in BaseRetrying.iter(self, retry_state)
    312 is_explicit_retry = fut.failed and isinstance(fut.exception(), TryAgain)
    313 if not (is_explicit_retry or self.retry(retry_state)):
--> 314     return fut.result()
    316 if self.after is not None:
    317     self.after(retry_state)

File /opt/anaconda3/envs/langchain/lib/python3.10/concurrent/futures/_base.py:451, in Future.result(self, timeout)
    449     raise CancelledError()
    450 elif self._state == FINISHED:
--> 451     return self.__get_result()
    453 self._condition.wait(timeout)
    455 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:

File /opt/anaconda3/envs/langchain/lib/python3.10/concurrent/futures/_base.py:403, in Future.__get_result(self)
    401 if self._exception:
    402     try:
--> 403         raise self._exception
    404     finally:
    405         # Break a reference cycle with the exception in self._exception
    406         self = None

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/tenacity/__init__.py:382, in Retrying.__call__(self, fn, *args, **kwargs)
    380 if isinstance(do, DoAttempt):
    381     try:
--> 382         result = fn(*args, **kwargs)
    383     except BaseException:  # noqa: B902
    384         retry_state.set_exception(sys.exc_info())  # type: ignore[arg-type]

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/langchain/chat_models/jinachat.py:242, in JinaChat.completion_with_retry.<locals>._completion_with_retry(**kwargs)
    240 @retry_decorator
    241 def _completion_with_retry(**kwargs: Any) -> Any:
--> 242     return self.client.create(**kwargs)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/openai/api_resources/chat_completion.py:25, in ChatCompletion.create(cls, *args, **kwargs)
     23 while True:
     24     try:
---> 25         return super().create(*args, **kwargs)
     26     except TryAgain as e:
     27         if timeout is not None and time.time() > start + timeout:

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py:153, in EngineAPIResource.create(cls, api_key, api_base, api_type, request_id, api_version, organization, **params)
    127 @classmethod
    128 def create(
    129     cls,
   (...)
    136     **params,
    137 ):
    138     (
    139         deployment_id,
    140         engine,
   (...)
    150         api_key, api_base, api_type, api_version, organization, **params
    151     )
--> 153     response, _, api_key = requestor.request(
    154         "post",
    155         url,
    156         params=params,
    157         headers=headers,
    158         stream=stream,
    159         request_id=request_id,
    160         request_timeout=request_timeout,
    161     )
    163     if stream:
    164         # must be an iterator
    165         assert not isinstance(response, OpenAIResponse)

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/openai/api_requestor.py:298, in APIRequestor.request(self, method, url, params, headers, files, stream, request_id, request_timeout)
    277 def request(
    278     self,
    279     method,
   (...)
    286     request_timeout: Optional[Union[float, Tuple[float, float]]] = None,
    287 ) -> Tuple[Union[OpenAIResponse, Iterator[OpenAIResponse]], bool, str]:
    288     result = self.request_raw(
    289         method.lower(),
    290         url,
   (...)
    296         request_timeout=request_timeout,
    297     )
--> 298     resp, got_stream = self._interpret_response(result, stream)
    299     return resp, got_stream, self.api_key

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/openai/api_requestor.py:700, in APIRequestor._interpret_response(self, result, stream)
    692     return (
    693         self._interpret_response_line(
    694             line, result.status_code, result.headers, stream=True
    695         )
    696         for line in parse_stream(result.iter_lines())
    697     ), True
    698 else:
    699     return (
--> 700         self._interpret_response_line(
    701             result.content.decode("utf-8"),
    702             result.status_code,
    703             result.headers,
    704             stream=False,
    705         ),
    706         False,
    707     )

File /opt/anaconda3/envs/langchain/lib/python3.10/site-packages/openai/api_requestor.py:763, in APIRequestor._interpret_response_line(self, rbody, rcode, rheaders, stream)
    761 stream_error = stream and "error" in resp.data
    762 if stream_error or not 200 <= rcode < 300:
--> 763     raise self.handle_error_response(
    764         rbody, rcode, resp.data, rheaders, stream_error=stream_error
    765     )
    766 return resp

AuthenticationError: Invalid token

[dosubot[bot]]

Answer generated by a 🤖

Answer

From your description, it appears that you're encountering an "AuthenticationError: Invalid token" error when trying to use the JinaChat service in the LangChain framework. This error typically arises when the API key used for authentication is invalid.

To address this issue, I would suggest verifying the API key you're using. You've set the API key in the environment variable JINACHAT_API_KEY as shown in your code:

os.environ["JINACHAT_API_KEY"] = "..."  # from https://cloud.jina.ai/settings/tokens

Please ensure that the API key you're using is valid and correctly copied from your JinaChat account. You can usually find this in your account settings on the JinaChat website or service.

However, please note that this is just one potential solution based on the information provided. If you've verified the API key and are still encountering the same issue, it's possible that there might be a problem with the JinaChat service itself, or the key might have been revoked or expired.

If you believe this is a bug that could impact other users, feel free to make a pull request with a proposed fix. If the issue persists after trying these steps, I would recommend checking if you're using the latest version of LangChain, as the issue might have been resolved in a more recent update.

Sources

• langchain/chat_models/jinachat.py

---

This response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

[delgermurun]

@benman1 did you get an api key from https://chat.jina.ai/api and set JINACHAT_API_KEY env?

[dudesparsh]

I tried replicating the same, and I confirm that I am also getting a similar error ( even after setting the JINA_API_KEY ). I assume that this model can't be implemented wrong, but for checking purpose - I just passed the API_KEY directly in my code - can that cause an error ? ( In case not, then @benman1 has a proper issue ).

[benman1]

@delgermurun thanks for clarifying,where to get the API keys for the chat. I found https://cloud.jina.ai/settings/tokens mentioned elsewhere, hence the confusion. I confirm it works with API key from the right place.

I've created a mini PR #7540 to clarify this in the Jina chat docstring.

[delgermurun]

@benman1 thanks a lot.

[delgermurun]

@dudesparsh just in case you missed it, the environment var key is JINACHAT_API_KEY, not JINA_API_KEY.

[dosubot[bot]]

Hi, @benman1! I'm Dosu, and I'm helping the LangChain team manage our backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, the issue you reported was related to authentication in the JinaChat module. You encountered an "AuthenticationError: Invalid token" when running the code. However, it seems that the issue has been resolved. Another user named dosu-beta suggested verifying the API key used for authentication, and you confirmed that using the correct API key resolved the issue. In fact, you have even created a pull request to update the Jina chat docstring to clarify this solution.

Before we close this issue, we wanted to check with you if it is still relevant to the latest version of the LangChain repository. If it is, please let us know by commenting on this issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your contribution and for helping us improve LangChain!

[hammad26]

I am trying to use Jina embedding model and facing authentication issue: The given Jina auth token is invalid. Please check your Jina auth token. (type=value_error)

The sample python code given on Jina Embedding page is:

import requests

url = 'https://api.jina.ai/v1/embeddings'

headers = {
  'Content-Type': 'application/json',
  'Authorization': 'Bearer jina_xxxxxxxx-xx'
}

data = {
  'input': ["Your text string goes here", "You can send multiple texts"],
  'model': 'jina-embeddings-v2-base-en'
}

response = requests.post(url, headers=headers, json=data)

Its using Bearer token there. On the other hand, sample code given on Lang Chain is:

from langchain.embeddings import JinaEmbeddings
jina_auth_token = 'Bearer jina_xxxxxxxx-xx'
# jina_auth_token = 'jina_xxxxxxxx-xx'
embeddings = JinaEmbeddings(
    jina_auth_token=jina_auth_token, model_name="ViT-B-32::openai"
)

I used both variations of token there i.e with and without Bearer but its giving me the authentication error.

[JoanFM]

I am trying to use Jina embedding model and facing authentication issue: The given Jina auth token is invalid. Please check your Jina auth token. (type=value_error)

The sample python code given on Jina Embedding page is:

import requests

url = 'https://api.jina.ai/v1/embeddings'

headers = {
  'Content-Type': 'application/json',
  'Authorization': 'Bearer jina_xxxxxxxx-xx'
}

data = {
  'input': ["Your text string goes here", "You can send multiple texts"],
  'model': 'jina-embeddings-v2-base-en'
}

response = requests.post(url, headers=headers, json=data)

Its using Bearer token there. On the other hand, sample code given on Lang Chain is:

from langchain.embeddings import JinaEmbeddings
jina_auth_token = 'Bearer jina_xxxxxxxx-xx'
# jina_auth_token = 'jina_xxxxxxxx-xx'
embeddings = JinaEmbeddings(
    jina_auth_token=jina_auth_token, model_name="ViT-B-32::openai"
)

I used both variations of token there i.e with and without Bearer but its giving me the authentication error.

Hey @hammad26 ,

I am going to fix the implementation to be able to use JinaEmbeddings properly after the new platform release